Featherless
- Categories
- Inference hosts
- Owned by
- (private) — Recursal AI
- Website
- https://featherless.ai
- Pricing page
- https://featherless.ai/pricing
- Fee model
- subscription+per_token
- Fees
- Chat plan $25/mo flat: unlimited tokens, 32K context, 4 concurrent units, human-driven chat only (no API/agent/production use). Developer plan from $50/mo in credits billed per token per model (up to 256K context, 100 concurrent units, credits never expire, only successful requests billed). Business: custom dedicated H100/MI325X/B200/B300
- Free tier
- no
- OpenAI-compatible API
- yes
- Notes
- 40,000+ open (Hugging Face) models on every plan; prompts/completions never stored; per-model rates from public /v1/models API (effective Developer-plan price incl. any niche-model multiplier); context served often 32K even where model supports more
- Sources
- https://featherless.ai/pricing https://featherless.ai/docs/request-pricing-and-credits https://api.featherless.ai/v1/models collected 2026-09-18
LLM prices (45 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepSeek V3 0324 deepseek-ai/DeepSeek-V3-0324 |
$0.385 | $1.62 | — | 131k | ✓ src src2 src3 |
| DeepSeek V3.1 deepseek-ai/DeepSeek-V3.1 |
$0.285 | $1 | — | 131k | ✓ src src2 src3 |
| DeepSeek V3.2 deepseek-ai/DeepSeek-V3.2 |
$0.264 | $0.41 | $0.06 | 131k | ✓ src src2 src3 |
| DeepSeek V4 Flash 0423 deepseek-ai/DeepSeek-V4-Flash |
$0.14 | $0.28 | — | 262k | ✓ src src2 src3 |
| DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-0731 |
$0.14 | $0.28 | — | 262k | ✓ src src2 src3 |
| DeepSeek V4 Pro 0423 deepseek-ai/DeepSeek-V4-Pro |
$1.60 | $3.20 | $0.20 | 262k | ✓ src src2 src3 |
| DeepSeek V4.1 Flash deepseek-ai/DeepSeek-V4.1-Flash |
$0.30 | $1.20 | — | 262k | ✓ src src2 src3 |
| Gemma 3 27B IT google/gemma-3-27b-it |
$0.10 | $0.30 | $0.08 | 33k | ✓ src src2 src3 |
| Gemma 4 26B A4B google/gemma-4-26B-A4B-it |
$0.07 | $0.34 | $0.05 | 33k | ✓ src src2 src3 |
| Gemma 4 31B google/gemma-4-31B-it |
$0.12 | $0.36 | $0.10 | 33k | ✓ src src2 src3 |
| GLM 4.6 zai-org/GLM-4.6 |
$0.55 | $2.20 | $0.11 | 203k | ✓ src src2 src3 |
| GLM 4.7 zai-org/GLM-4.7 |
$0.55 | $2.20 | $0.11 | 203k | ✓ src src2 src3 |
| GLM 4.7 Flash zai-org/GLM-4.7-Flash |
$0.065 | $0.40 | — | 203k | ✓ src src2 src3 |
| GLM 5 zai-org/GLM-5 |
$0.95 | $3.15 | $0.19 | 203k | ✓ src src2 src3 |
| GLM 5.1 zai-org/GLM-5.1 |
$1.30 | $4.30 | $0.26 | 203k | ✓ src src2 src3 |
| GLM-5.2 zai-org/GLM-5.2 |
$1.40 | $4.40 | $0.15 | 262k | ✓ src src2 src3 |
| GLM-5.3 zai-org/GLM-5.3 |
$1.40 | $4.40 | — | 262k | ✓ src src2 src3 |
| GLM-5.3 Flash zai-org/GLM-5.3-Flash |
$0.15 | $0.50 | $0.03 | 262k | ✓ src src2 src3 |
| gpt-oss-120b openai/gpt-oss-120b |
$0.15 | $0.60 | $0.02 | 131k | ✓ src src2 src3 |
| gpt-oss-20b openai/gpt-oss-20b |
$0.04 | $0.15 | — | 131k | ✓ src src2 src3 |
| Kimi K2 0711 moonshotai/Kimi-K2-Instruct |
$0.60 | $2.50 | — | 33k | ✓ src src2 src3 |
| Kimi K2 0905 moonshotai/Kimi-K2-Instruct-0905 |
$0.60 | $2.50 | — | 33k | ✓ src src2 src3 |
| Kimi K2 Thinking moonshotai/Kimi-K2-Thinking |
$0.60 | $2.50 | — | 33k | ✓ src src2 src3 |
| Kimi K2.5 moonshotai/Kimi-K2.5 |
$0.80 | $3.40 | $0.154 | 262k | ✓ src src2 src3 |
| Kimi K2.6 moonshotai/Kimi-K2.6 |
$0.80 | $3.40 | $0.154 | 262k | ✓ src src2 src3 |
| Kimi K2.7 Code moonshotai/Kimi-K2.7-Code |
$0.80 | $3.40 | $0.154 | 262k | ✓ src src2 src3 |
| Llama 3.1 8B Instruct meta-llama/Llama-3.1-8B-Instruct |
$0.05 | $0.08 | $0.028 | 33k | ✓ src src2 src3 |
| Llama 3.3 70B Instruct meta-llama/Llama-3.3-70B-Instruct |
$0.65 | $0.75 | $0.52 | 33k | ✓ src src2 src3 |
| MiniMax M2 MiniMaxAI/MiniMax-M2 |
$0.278 | $1.11 | $0.056 | 205k | ✓ src src2 src3 |
| MiniMax M2.1 MiniMaxAI/MiniMax-M2.1 |
$0.30 | $1.20 | $0.06 | 205k | ✓ src src2 src3 |
| MiniMax M2.5 MiniMaxAI/MiniMax-M2.5 |
$0.295 | $1.20 | $0.059 | 205k | ✓ src src2 src3 |
| MiniMax M2.7 MiniMaxAI/MiniMax-M2.7 |
$0.30 | $1.20 | $0.06 | 205k | ✓ src src2 src3 |
| MiniMax M3 MiniMaxAI/MiniMax-M3 |
$0.55 | $2.20 | $0.06 | 262k | ✓ src src2 src3 |
| Mistral Nemo mistralai/Mistral-Nemo-Instruct-2407 |
$0.217 | $0.247 | $0.20 | 33k | ✓ src src2 src3 |
| Mistral Small 3.2 24B mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
$0.217 | $0.403 | — | 33k | ✓ src src2 src3 |
| Qwen2.5 72B Instruct Qwen/Qwen2.5-72B-Instruct |
$0.37 | $0.40 | — | 33k | ✓ src src2 src3 |
| Qwen3 32B Qwen/Qwen3-32B |
$0.102 | $0.493 | $0.082 | 33k | ✓ src src2 src3 |
| Qwen3 Coder 480B A35B Qwen/Qwen3-Coder-480B-A35B-Instruct |
$0.38 | $1.55 | $0.076 | 33k | ✓ src src2 src3 |
| Qwen3 Next 80B A3B Qwen/Qwen3-Next-80B-A3B-Instruct |
$0.125 | $1.15 | — | 33k | ✓ src src2 src3 |
| Qwen3-30B-A3B-Instruct-2507 Qwen/Qwen3-30B-A3B-Instruct-2507 |
$0.125 | $0.45 | — | 262k | ✓ src src2 src3 |
| Qwen3.5-397B-A17B Qwen/Qwen3.5-397B-A17B |
$0.55 | $3.50 | — | 262k | ✓ src src2 src3 |
| Qwen3.6 27B Qwen/Qwen3.6-27B |
$0.32 | $2.70 | $0.064 | 33k | ✓ src src2 src3 |
| Qwen3.6 35B A3B Qwen/Qwen3.6-35B-A3B |
$0.186 | $1.11 | $0.032 | 33k | ✓ src src2 src3 |
| Qwen3.8-27B Qwen/Qwen3.8-27B |
$0.40 | $3 | $0.15 | 262k | ✓ src src2 src3 |
| R1 0528 deepseek-ai/DeepSeek-R1-0528 |
$0.385 | $1.62 | — | 131k | ✓ src src2 src3 |